Agent Memory Leaderboard Cycle 2 results: MemoraX tops code memory track at 68.00 points

nikola_mr64990 · x · 2026-11-19

Agent Memory Leaderboard (AML) Cycle 2 results are out: 402 task submissions and 292 valid leaderboard entries across three tracks — text, code, and multimodal memory — testing whether AI agents can actually learn from past experience.

Teams came from Alibaba Cloud DMS, Shopee, OPPO, KT, OceanBase, plus universities, memory startups, and independent developers. MemoraX leads the Code Memory Commercial Products ranking with 68.00 points. The benchmark positions memory as a measurable dimension of agent capability.

Related event: Agent Memory Leaderboard Cycle 2 Released, MemoraX Tops Rankings(2 posts)→

Original post →

More from coding & agent

coding & agent channel →